Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Monte carlo simulation

14,855 views

Published on

Monte carlo simulation

Published in: Engineering
  • Login to see the comments

Monte carlo simulation

  1. 1. Monte Carlo Simulation PRESENTER: RAJESH PIRYANI SOUTH ASIAN UNIVERSITY
  2. 2. Outline Introduction History Examples Advantages Demonstration with Excel
  3. 3. What is simulation Simulation is the imitation of the operation of real world process or system over time. To engage Modelling and simulation, first create a model approximating an event. The model is then followed by simulation, which allows for the repeated observation of the model. After one or many simulations of the model, a third step takes place and that is analysis ..  Analysis aids in the ability to draw conclusions, verify and validate the research, and make recommendations based on various iterations or simulations of the model. Simulation is defined to be a method that utilizes sequences of random numbers as data.
  4. 4. What is Monte Carlo
  5. 5. What is Monte Carlo Simulation? This techniques can be used in different domain Complex Integral Computation Economics Specially in Risk Management extensively used in financial institutions to compute European prices, to evaluate sensitivities of portfolios to various parameters and to compute risk measurements Statistical simulation technique that provides approximate solution to problems expressed mathematically. It utilize the sequence of random number to perform the simulation.
  6. 6. Why Monte Carlo Simulations Simple implementation on computer Applicable for complex problems that are otherwise intractable Simulation does not produce an exact answer but in fact is a statistical estimate with error The most common use of Monte Carlo Method is the evaluation of Integral and calculation of Mathematically constant variable such as PI.
  7. 7. History 1930’s: Enrico Fermi uses Monte Carlo in the calculation of neutron diffusion. 1940’s: Stan Ulam while playing solitaire tries to calculate the likelihood of winning based on the initial layout of the cards. After exhaustive combinatorial calculations, he decided to go for practical approach He tries many different layouts and observing the number of successful games. He realized that computers could be used to solve such problems. Stan Ulam worked with John Von Neumann to develop algorithms including importance sampling and rejection sampling. Ulam and Von Neumann suggested that aspects of research into nuclear fission at Los Alamos could be aided by use of computer experiments based on chance
  8. 8. History The project was top secret so Von Neumann chose the name Monte Carlo in reference to the Casino in Monaco. 1950’s: Many papers on Monte Carlo simulation appeared in physics literature. The first major MCMC paper was published by Metropolis et al in 1953. 1970: Generalization of the Metropolis algorithm by Hastings which led to development of MCMC 1980’s: Important MCMC papers appeared in the fields of computer vision and artificial intelligence but there were few significant publications in the field of statistics 1990: MCMC made the first significant impact in statistics in the work of Gelfand and Smith.
  9. 9. History In the last 20 years MCMC has become a widely used tool in several fields and much research progress has been made. Monte Carlo Methods are now used to solve problems in numerous fields including applied statistics, engineering, finance and business, design and visuals, computing, telecommunications, and the physical sciences.
  10. 10. Monte Carlo Example: Estimation of PI
  11. 11. Estimating PI (Continued ..) If you are a very poor dart player, it is easy to imagine throwing darts randomly at the figure, and it should be apparent that of the total number of darts that hit within the square, the number of darts that hit the shaded part (circle quadrant) is proportional to the area of that part. In other words,
  12. 12. Estimating PI (Continued ..) If you remember your geometry, it's easy to show that
  13. 13. (x, y) Estimating PI (Continued ..) x = (random#) y = (random#) distance = sqrt (x^2 + y^2) if distance.from.origin (less.than.or.equal.to) 1.0 let hits = hits + 1.0
  14. 14. Estimating PI (Continued ..)
  15. 15. A Simple Integral Consider the simple integral: This can be evaluated in the same way as the pi example. By randomly tossing darts at a graph of the function and tallying the ratio of hits inside and outside the function.
  16. 16. A Simple Integral (continued…) R = {(x,y): a  x  b, 0  y  max f(x)} Randomly tossing 100 or so darts we could approximate the integral… I = [fraction under f(x)] * (area of R) This assumes that the dart player is throwing the darts randomly, but not so random as to miss the square altogether.
  17. 17. A Simple Integral (continued…) Generally, the more iterations of the game the better the approximation will be. 1000 or more darts should yield a more accurate approximation of the integral than 100 or fewer. The results can quickly become skewed and completely irrelevant if the games random numbers are not sufficiently random.
  18. 18. Advantages Probabilistic Results. Results show not only what could happen, but how likely each outcome is. Graphical Results. ◦ it’s easy to create graphs of different outcomes and their chances of occurrence. ◦ This is important for communicating findings to other stakeholders. Sensitivity Analysis. ◦ With just a few cases, deterministic analysis makes it difficult to see which variables impact the outcome the most. ◦ In Monte Carlo simulation, it’s easy to see which inputs had the biggest effect on bottom-line results.
  19. 19. Advantages Scenario Analysis: In deterministic models, it’s very difficult to model different combinations of values for different inputs to see the effects of truly different scenarios. ◦ Using Monte Carlo simulation, analysts can see exactly which inputs had which values together when certain outcomes occurred. Correlation of Inputs. In Monte Carlo simulation, it’s possible to model interdependent relationships between input variables. ◦ It’s important for accuracy to represent how, in reality, when some factors goes up, others go up or down accordingly.
  20. 20. References 1. Sabri Pllana. History of Monte Carlo method. August 2000. URL http://www.geocities.com/CollegePark/Quad/2435/index.html. http://www.geocities.com/CollegePark/Quad/2435/index.html, 2. http://www.ecs.fullerton.edu/~mathews/fofz/dirichlet/dirichle.html 3. http://mathworld.wolfram.com/DirichletProblem.html 4. http://wwitch.unl.edu/zeng/joy/mclab/mcintro.html 5. Farlow, Stanley Partial Differential Equations for Scientists and Engineers Dover Publications, New York 1982
  21. 21. Thank You

×